{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"1406.2807","title":"The Secrets of Salient Object Segmentation","created":"2014-06-11","cited_by_count":200},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"1902.03751","title":"Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded","created":"2019-02-11","cited_by_count":128},{"id":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"1708.01471","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","created":"2017-08-04","cited_by_count":117},{"id":"1812.05252","title":"Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering","created":"2018-12-13","cited_by_count":114},{"id":"1606.03556","title":"Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?","created":"2016-06-11","cited_by_count":111},{"id":"1812.10025","title":"Attention Branch Network: Learning of Attention Mechanism for Visual Explanation","created":"2018-12-25","cited_by_count":109},{"id":"1705.03854","title":"Predicting the Driver's Focus of Attention: the DR(eye)VE Project","created":"2017-05-10","cited_by_count":79},{"id":"2002.10215","title":"On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering","created":"2020-02-24","cited_by_count":78},{"id":"1905.09998","title":"Self-Critical Reasoning for Robust Visual Question Answering","created":"2019-05-24","cited_by_count":61},{"id":"1910.10706","title":"KnowIT VQA: Answering Knowledge-Based Questions about Videos","created":"2019-10-23","cited_by_count":53},{"id":"2005.14310","title":"Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning","created":"2020-05-28","cited_by_count":53},{"id":"1505.03581","title":"CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research","created":"2015-05-14","cited_by_count":52},{"id":"1803.05268","title":"Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning","created":"2018-03-14","cited_by_count":51},{"id":"1312.7570","title":"Actions in the Eye: Dynamic Gaze Datasets and Learnt Saliency Models for Visual Recognition","created":"2013-12-29","cited_by_count":37},{"id":"1709.06308","title":"Exploring Human-like Attention Supervision in Visual Question Answering","created":"2017-09-19","cited_by_count":36},{"id":"1808.00265","title":"Interpretable Visual Question Answering by Visual Grounding from Attention Supervision Mining","created":"2018-08-01","cited_by_count":28},{"id":"2007.14419","title":"AiR: Attention with Reasoning Capability","created":"2020-07-28","cited_by_count":28},{"id":"1909.11874","title":"Compact Trilinear Interaction for Visual Question Answering","created":"2019-09-26","cited_by_count":24},{"id":"1812.11004","title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning","created":"2018-12-26","cited_by_count":18},{"id":"2001.03339","title":"Visual Question Answering on 360{\\deg} Images","created":"2020-01-10","cited_by_count":15},{"id":"1704.07434","title":"Paying Attention to Descriptions Generated by Image Captioning Models","created":"2017-04-24","cited_by_count":12},{"id":"1705.10546","title":"Saliency Revisited: Analysis of Mouse Movements versus Fixations","created":"2017-05-30","cited_by_count":12},{"id":"1911.08618","title":"Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA","created":"2019-11-19","cited_by_count":12},{"id":"1604.01574","title":"PET: An Eye-tracking Dataset for Animal-centric PASCAL Object Classes","created":"2016-04-06","cited_by_count":5},{"id":"1810.03821","title":"Knowing Where to Look? Analysis on Attention of Visual Question Answering System","created":"2018-10-09","cited_by_count":1}],"next_cursor":null}